基于SUSAN算法的遥感图像去云  

Cloud removal from satellite imagery based on SUSAN algorithm

作　　者：卢力[1] 王勇涛[1] 田金文[1] 柳健[1] 

机构地区：[1]华中科技大学多谱信息处理国防重点实验室

出　　处：《通信学报》2006年第8期160-164,共5页Journal on Communications

摘　　要：提出了一种基于SUSAN算法自动消去主图像中云区遮挡影响的方法。该方法首先利用SUSAN算法有效提取主图像和参考图像中的角点,然后采用概率松弛法寻找主图像和参考图像间的匹配点,将主图像与参考图像配准,在此基础上搜索主图像的云区,最后进行融合得到去云图像。实验结果表明该方法具有较好的去云效果。A new image fusion scheme that could automate remove the cloud covers in the main image was proposed based on SUSAN algorithm. First, the corners were found both in the main image and the reference image based on SUSAN algorithm, and then the matched corners were found using probabilistic relaxation algorithm to register the reference image to the main image. Finally, a cloud-removed image was obtained by fusion. The performance of the proposed scheme is demonstrated experimentally.

关 键 词：去云 图像配准 SUSAN算法 概率松弛法 图像融合 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]